Embedding Models for Multivariate Time Series Anomaly Detection in Industry 5.0
Data Science and Engineering · 2026-06 · 11 (2) · 378-394
DOI: 10.1007/s41019-025-00295-w ↗Kurz gefasst
Fachartikel in der Zeitschrift Data Science and Engineering, online erschienen am 24.06.2025. Verfasst von Lorenzo Colombi und 10 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministero dell’Istruzione, dell’Università e della Ricerca.
Abstract (Originalsprache)
Industrial processes often involve the generation—and the analysis—of multivariate time series data, which poses several challenges from the anomaly detection perspective. In addition to the need to detect previously unseen anomalies, the high dimensionality of industrial datasets introduces the complexity of simultaneously analyzing multiple features and their interactions. Finally, industrial datasets are typically highly imbalanced, with minimal information on anomalous processes. To address these issues, we propose a novel anomaly detection framework that introduces two embedding models, based on Time2Vec and Discrete Wavelet Transforms, leveraging their capabilities to represent multivariate time series as vectors while capturing and preserving temporal dependencies and combining them with several classifiers to enhance the overall performance of anomaly detection. We tested our solution using a publicly available benchmark dataset and a real industrial use case, particularly data collected from a Bonfiglioli gear manufacturing plant. The results demonstrate that, unlike traditional reconstruction-based autoencoders, which often struggle with sporadic noise, our embedding-based solutions maintain high performance across various noise conditions.
Förderung
- Ministero dell’Istruzione, dell’Università e della Ricerca
Zitieren
APA
Colombi, L., Vespa, M., Belletti, N., Brina, M., Dahdal, S., Tabanelli, F., Resca, F., Bellodi, E., Tortonesi, M., Stefanelli, C., & Vignoli, M. (2026). Embedding Models for Multivariate Time Series Anomaly Detection in Industry 5.0. Data Science and Engineering, 11(2), 378-394. https://doi.org/10.1007/s41019-025-00295-w
Vancouver
Colombi L, Vespa M, Belletti N, Brina M, Dahdal S, Tabanelli F, et al. Embedding Models for Multivariate Time Series Anomaly Detection in Industry 5.0. Data Science and Engineering. 2026;11(2):378-394. doi:10.1007/s41019-025-00295-w
BibTeX
@article{Colombi2026,
author = {Colombi, Lorenzo and Vespa, Michela and Belletti, Nicolas and Brina, Matteo and Dahdal, Simon and Tabanelli, Filippo and Resca, Francesco and Bellodi, Elena and Tortonesi, Mauro and Stefanelli, Cesare and Vignoli, Massimiliano},
title = {Embedding Models for Multivariate Time Series Anomaly Detection in Industry 5.0},
journal = {Data Science and Engineering},
year = {2026},
volume = {11},
number = {2},
pages = {378--394},
doi = {10.1007/s41019-025-00295-w}
}
EUVIMED